Simulation-based digital twinborn visualization technology method and system
Through simulated digital twin visualization technology, a traffic flow simulation model and virtual traffic scene are established, data is collected and processed in real time, and the dynamic signal optimization algorithm is used to adjust the traffic light matching time, which solves the problem that traditional solutions cannot adapt to changes in traffic flow in real time, achieving reduction Waiting time and congestion effect.
Patent Information
- Application Number
- CN202411004647.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The traditional traffic light timing scheme cannot adapt to changes in traffic flow in real time, resulting in too long waiting time for vehicles and frequent traffic congestion.
Using simulation digital twin visualization technology, we can predict traffic flow changes by establishing a traffic flow simulation model, build virtual traffic scenes, collect and process traffic data in real time, and use dynamic signal optimization algorithm to automatically adjust the timing of traffic lights to reduce waiting time and congestion. .
It realizes dynamic adjustment of signal timing based on real-time traffic data, reduces vehicle waiting time and traffic congestion, improves road traffic capacity, and ensures smooth traffic flow.
Smart Images

Figure CN119003905A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of digital twin visualization technology, and specifically to a simulation-based digital twin visualization technology method and system. Background Art
[0002] Digital twin refers to the modeling and simulation of physical entities in the real world through digital models, and the analysis and optimization in virtual space to provide support for the design, production and operation of entities. Visualization is a technology or method that presents data or information in a visual form through graphics, charts, images or animations. Digital twin visualization is to visualize the digital twin model through images, animations or interactive interfaces, so that users can understand and operate digital twins more intuitively. Digital twin technology presents physical objects, systems or processes in the real world in virtual space through digital modeling, so that we can conduct real-time monitoring, analysis and prediction. In the past few years, digital twin visualization has been widely used in industries such as smart water conservancy, smart campus, smart factory and smart city, and has achieved remarkable results.
[0003] However, the current simulation digital twin visualization technology still has certain shortcomings in the field of smart transportation. With the accelerated advancement of urbanization, traffic congestion is becoming increasingly serious. Traditional traffic light timing schemes have defects. Traditional traffic light timing schemes are often based on fixed time periods and preset modes, and cannot adapt to changes in traffic flow in real time, resulting in long waiting times for vehicles and frequent traffic congestion. Therefore, it is necessary to propose a method and system based on simulation digital twin visualization technology to solve the problems in the existing technology. Summary of the invention
[0004] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a method and system based on simulation digital twin visualization technology. It can use simulation models to predict traffic flow changes, build virtual traffic scenes through digital twin technology, simulate traffic operation conditions in real time, and display traffic flow data and signal timing plans based on visualization technology, so as to dynamically adjust the timing of traffic lights and reduce waiting time and congestion.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method based on simulation digital twin visualization technology, the method comprising:
[0006] Establish a traffic flow simulation model to predict changes in traffic flow;
[0007] Build a digital twin scenario corresponding to the actual traffic scenario to reflect the actual traffic operation situation in real time;
[0008] Collect traffic flow and vehicle driving status data in real time;
[0009] Process and analyze the collected data to extract useful information;
[0010] Display traffic flow data and signal timing plans through visualization technology;
[0011] Based on real-time data and the prediction results of the simulation model, the dynamic signal optimization algorithm automatically calculates the optimal signal timing plan and adjusts the actual timing of traffic lights.
[0012] Furthermore, the traffic flow simulation model is established to predict changes in traffic flow, and the method includes:
[0013] Collect historical traffic flow data, basic information on road network layout and vehicle driving rules, and pre-process the collected data;
[0014] Use graph theory to represent the road network, where nodes represent intersections and edges represent road segments, and define the physical and traffic properties of each road segment;
[0015] The following model is used to describe the interaction between vehicles. The formula is: Among them, v n+1 (t+Δt) is the speed of the following vehicle at the future time, v n (t) is the speed of the preceding vehicle at the current moment, Δt is the time step, and T is the driver’s reaction time V(s n+1 (t)) is based on the vehicle spacing s n+1 (t) determine the expected speed;
[0016] A lane-changing model is introduced to handle vehicle lane-changing behavior;
[0017] Design signal phases and timing schemes, including the allocation of green, yellow and red light times, and consider the transition logic and conflict resolution mechanisms between different phases;
[0018] According to the above model, the vehicle driving and intersection signal control process are simulated, and the simulation results, including traffic flow, vehicle delay and queue length indicators, are recorded and output.
[0019] Furthermore, the method of constructing a digital twin scene corresponding to an actual traffic scene includes:
[0020] Map physical objects in actual traffic scenarios to digital twin scenarios and establish a real-time data synchronization mechanism;
[0021] Use 3D modeling technology to build virtual traffic scenes, and simulate road layout, vehicle driving trajectory and signal control status in a virtual environment based on the road network model and vehicle driving model;
[0022] Connect real-time traffic data to the digital twin scene through interfaces and protocols, and use visualization technology to display real-time information on vehicle location, speed, and traffic signal status in a virtual environment;
[0023] Add interactive elements, including buttons and sliders, to the digital twin scene, allowing users to adjust signal timing plans and view traffic operation conditions in different scenarios through the interface.
[0024] Furthermore, the real-time collection of traffic flow and vehicle driving status data comprises:
[0025] Deploy sensor equipment at key traffic nodes, including cameras, radars, and geomagnetic sensors at intersections and highway entrances and exits;
[0026] Collect traffic flow, vehicle speed, vehicle type, and lane occupancy data from sensor devices in real time through wired and wireless methods;
[0027] The collected data is fused to integrate the data from different sensors into a consistent information stream. The Kalman filter algorithm is used to estimate and predict the vehicle state. The Kalman filter state update equation is: in, is the updated state estimate, is the predicted state, K k is the Kalman gain, z k is the observed value, H k is the observation matrix;
[0028] Store data in databases and data warehouses, and transmit collected data to traffic signal optimization systems.
[0029] Furthermore, the collected data is processed and analyzed to extract useful information, and the method includes:
[0030] Check if there are identical records in the dataset and remove duplicates;
[0031] For missing and incomplete data fields, fill them in based on the context;
[0032] For data containing noise, the Kalman filter algorithm is used to remove the noise;
[0033] Use statistics to define the threshold of outliers and detect data points that exceed the threshold. Use the Z-score method to detect outliers: Where X is the data point, μ is the mean, σ is the standard deviation, and |Z|>3 is considered an outlier;
[0034] Data aggregation and statistical analysis: Aggregate data by time intervals, calculate average flow and average speed indicators, aggregate data to different sections and intersections according to the road network layout, calculate traffic flow and congestion levels in each area, and use statistical methods to further analyze data to extract traffic flow patterns and congestion hotspot information;
[0035] Key features for signal optimization are extracted from the processed data, including traffic flow peak, average waiting time, and intersection saturation.
[0036] Furthermore, the method of displaying traffic flow data and signal timing scheme by visualization technology includes:
[0037] Obtain processed traffic flow data and signal timing plan data from the real-time data acquisition and processing module;
[0038] Select visualization libraries and frameworks to create visualization charts and interfaces, determine the type and layout of visualization elements, use heat maps to display traffic congestion, and use kernel density estimation to generate heat maps, involving the following formulas: Among them, K is the kernel function, h is the bandwidth, and x i is the observed data point, n is the number of data points;
[0039] Design a user-friendly interface, including navigation bars, toolbars, and chart areas, determine the data that needs to be visualized, and select appropriate visual representations for each data type;
[0040] Map data onto visual elements;
[0041] Graphically represent the signal timing scheme, including using different colors of lights to represent different signal light states and displaying the real-time status of the signal lights on a map;
[0042] Use visualization tools and techniques to render the designed interface and data into visual charts;
[0043] Optimize the visual interface, including adjusting colors, fonts, and layout.
[0044] Furthermore, the method of automatically calculating the optimal signal timing scheme based on the real-time data and the prediction results of the simulation model through a dynamic signal optimization algorithm and adjusting the actual timing of the traffic lights includes:
[0045] The real-time traffic flow and vehicle driving status data provided by the real-time data acquisition and processing module are integrated with the predicted data of the traffic flow simulation module;
[0046] Extract key features from the fused data, including current traffic flow, vehicle queue length, average speed, and predicted future traffic flow trends;
[0047] Use the dynamic signal optimization algorithm based on reinforcement learning to optimize dynamic signals;
[0048] Generate the optimal signal timing plan based on the calculation results of the dynamic signal optimization algorithm;
[0049] The generated optimal signal timing plan is transmitted to the traffic light control system, and the control system adjusts the actual timing of the traffic light according to the received signal timing plan.
[0050] Furthermore, the dynamic signal optimization algorithm using reinforcement learning is used to perform dynamic signal optimization, and the reinforcement learning algorithm works in the following manner:
[0051] State definition: Define the current traffic state as the state s of the algorithm t , including traffic volume and vehicle queue length;
[0052] Action selection: according to the current state s t , the algorithm selects a signal timing scheme as action a t ;
[0053] Reward calculation: After the action is implemented, the reward r is calculated based on the performance of the traffic system t , including reduced vehicle waiting time and reduced congestion;
[0054] Strategy update: According to the reward r t and state transition, update strategy π(a t |s t ), that is, the probability of choosing different actions in different states;
[0055] formula: Among them, α is the learning rate, γ is the discount factor, Q(s t ,a t ) is the value function of a state-action pair.
[0056] A simulation digital twin visualization technology system, the system comprising:
[0057] Traffic flow simulation module, based on historical traffic flow data, road network layout, and vehicle driving rules information, builds a high-precision traffic flow simulation model to simulate actual traffic operation and predict future traffic flow trends;
[0058] The digital twin module uses digital twin technology to build a virtual traffic scene corresponding to the actual traffic scene, reflecting the actual traffic operation situation in real time;
[0059] Real-time data collection and processing module, which collects traffic flow and vehicle driving status data in real time through sensors and camera equipment, transmits it to the system for processing and analysis, and extracts useful information for traffic signal optimization;
[0060] The visualization display module uses visualization technology to graphically display the traffic flow data and signal timing schemes in the simulation model and digital twin scene to the user, so that the user can intuitively understand the traffic operation status through the interface;
[0061] The dynamic signal optimization algorithm module automatically calculates the optimal signal timing plan based on the real-time collected traffic flow data and the prediction results of the simulation model through the dynamic signal optimization algorithm, and adjusts the actual timing of traffic lights in real time to reduce vehicle waiting time and traffic congestion.
[0062] Furthermore, the visual display module also includes an interactive interface, allowing the user to adjust the signal timing plan as needed and view the adjusted traffic operation effect in real time.
[0063] Compared with the existing technology, the simulation digital twin visualization technology method and system have the following beneficial effects:
[0064] The present invention simulates the actual traffic operation situation through a simulation model and predicts the changing trend of future traffic flow. It constructs a virtual traffic scene through digital twin technology, simulates the traffic operation situation in real time, and uses a dynamic signal optimization algorithm to automatically adjust the signal timing according to real-time traffic data. It also displays traffic flow data and signal timing plans based on visualization technology, so that traffic managers can intuitively understand the traffic operation situation, facilitate rapid response to emergencies, dynamically adjust the timing of traffic lights, reduce waiting time and congestion, ensure smooth traffic flow, and improve road capacity.
[0065] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0066] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0067] Figure 1 It is a flow chart of a simulation digital twin visualization technology method;
[0068] Figure 2 It is a structural schematic diagram of a simulation digital twin visualization technology system. DETAILED DESCRIPTION
[0069] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0070] Embodiment 1
[0071] A method for visualization technology based on simulation digital twins, the method comprising:
[0072] A traffic flow simulation model is established to predict changes in traffic flow, including: collecting historical traffic flow data, basic information on road network layout and vehicle driving rules, preprocessing the collected data, including data cleaning (removing outliers, duplicate values, etc.), data format conversion and normalization, establishing a road network model, using graph theory to represent the road network, where nodes represent intersections and edges represent road sections, defining the physical properties (physical properties include: length, number of lanes, speed limit) and traffic attributes (traffic attributes include: capacity and saturation) of each road section.
[0073] The vehicle driving model is constructed by applying the following model (such as Newell model, Gipps model, etc.) to describe the interaction between vehicles. The formula is: Among them, v n+1 (t+Δt) is the speed of the following vehicle at the future time, v n (t) is the speed of the preceding vehicle at the current moment, Δt is the time step, and T is the driver’s reaction time V(s n+1 (t)) is based on the vehicle spacing s n+1 (t) Determine the expected speed and introduce a lane changing model (such as the lane changing rules in the MITSIM model) to handle the vehicle lane changing behavior.
[0074] Intersection signal control model, design signal phase and timing scheme, including the allocation of green light time, yellow light time and red light time, consider the conversion logic and conflict resolution mechanism between different phases, simulation operation and result output, according to the above model, simulate vehicle driving and intersection signal control process, record and output simulation results, including key indicators such as traffic flow, vehicle delay and queue length.
[0075] Constructing a digital twin scene corresponding to the actual traffic scene to reflect the actual traffic operation situation in real time, the method includes:
[0076] Map physical objects in actual traffic scenes (such as vehicles, roads, intersections, etc.) to digital twin scenes, establish a real-time data synchronization mechanism, ensure that the data in the digital twin scenes is consistent with the actual traffic scenes, use 3D modeling technology (including Unity, Unreal Engine) to build virtual traffic scenes, and simulate road layouts, vehicle driving trajectories, and signal control status in virtual environments based on road network models and vehicle driving models.
[0077] Real-time traffic data is connected to the digital twin scene through interfaces and protocols (such as WebSocket, REST API, etc.), and real-time information on vehicle position, speed, and traffic signal status is displayed in a virtual environment using visualization technology (such as WebGL, Three.js, etc.). Interactive elements, including buttons and sliders, are added to the digital twin scene, allowing users to adjust signal timing plans and view traffic operation conditions in different scenarios through the interface, realizing real-time interaction between user input and simulation models, and ensuring that user operations can be reflected in the virtual scene in real time.
[0078] Optimize the performance of digital twin scenarios to ensure stable operation under high load conditions, evaluate the accuracy and real-time performance of digital twin scenarios, and make necessary adjustments and improvements based on the evaluation results.
[0079] Embodiment 2
[0080] Collect traffic flow and vehicle driving status data in real time.
[0081] The method includes: deploying sensor equipment at key traffic nodes, including cameras, radars and geomagnetic sensors at intersections and highway entrances and exits, ensuring that the sensors can cover the traffic areas that need to be monitored and can work stably and reliably, and collecting traffic flow, vehicle speed, vehicle type, and lane occupancy data from sensor equipment in real time through wired and wireless methods. The data collection system needs to be highly reliable and real-time to ensure the integrity and timeliness of the data.
[0082] Use multiple types of sensors (such as cameras and radars) to perform data fusion on the collected data, integrate the data from different sensors into a consistent information stream, and use the Kalman filter algorithm to estimate and predict the vehicle state during data fusion. A basic formula of the Kalman filter is the state update equation: in, is the updated state estimate, is the predicted state, K k is the Kalman gain, z k is the observed value, H k is the observation matrix.
[0083] The data is stored in databases and data warehouses for subsequent analysis and query. If needed, a distributed storage system can be used to improve the concurrency and scalability of data processing, and the collected data can be transmitted to the traffic signal optimization system or other systems that require this data. The security and integrity of the data must be ensured during the transmission process, and encryption and verification mechanisms can be used.
[0084] The collected data is processed and analyzed to extract useful information. The method includes: checking whether there are exactly the same records in the data set and deleting duplicates. For missing and incomplete data fields, they are filled in according to the context (such as using mean, median, mode, etc.) or marked as missing values. For data containing noise (such as vehicle speed, position, etc.), the Kalman filter algorithm is used to remove noise.
[0085] Use statistics to define the threshold of outliers and detect data points that exceed the threshold. Use the Z-score method to detect outliers: Where X is the data point, μ is the mean, σ is the standard deviation, and |Z|>3 is considered an outlier. Data aggregation and statistical analysis: aggregate the data at time intervals (such as every 5 minutes, every 1 hour), calculate the average flow and average speed indicators, and aggregate the data to different sections and intersections according to the road network layout. Calculate the traffic flow and congestion level in each area. Use statistical methods (such as regression analysis, cluster analysis, etc.) to further analyze the data, extract traffic flow patterns and congestion hotspot information, and extract key features of signal optimization from the processed data, including traffic flow peak, average waiting time, and intersection saturation.
[0086] Traffic flow data and signal timing schemes are displayed through visualization technology. The method includes: obtaining processed traffic flow data and signal timing scheme data from a real-time data acquisition and processing module, and performing necessary aggregation or conversion on the data so as to effectively display it in a visualization interface. For example, time series data is aggregated at time intervals (such as every 5 minutes), and statistical indicators such as average flow and maximum flow are calculated.
[0087] Select appropriate visualization libraries and frameworks (such as D3.js, ECharts, Tableau, etc.) to create visualization charts and interfaces, determine the types of visualization elements (such as line charts, heat maps, scatter plots, map layers, etc.) and layouts, and use heat maps to display traffic congestion. Assuming that kernel density estimation is used to generate heat maps, the following formulas are involved: Among them, K is the kernel function, h is the bandwidth, and x i is the observed data point, n is the number of data points. In practical applications, these calculations are usually done automatically by the visualization library.
[0088] Design a user-friendly interface, including navigation bars, toolbars, and chart areas. Determine the data that needs to be visualized and select appropriate visualizations for each data type. Map the data to visualization elements, for example, map traffic flow data to the Y-axis of a line chart and time to the X-axis. Represent the signal timing scheme in a graphical form, including using different colors of lights to represent different signal light states and displaying the real-time status of signal lights on a map.
[0089] Use visualization tools and techniques to render the designed interface and data into visual charts, ensure that the charts can be updated in real time to reflect the latest traffic flow and signal timing information, optimize the visual interface, including adjusting colors, fonts, and layout to improve readability and user experience, and make necessary adjustments based on user feedback and actual needs.
[0090] Embodiment 3
[0091] According to the prediction results of real-time data and simulation models, the optimal signal timing plan is automatically calculated through a dynamic signal optimization algorithm, and the actual timing of traffic lights is adjusted. The method includes: fusing the real-time traffic flow and vehicle driving status data provided by the real-time data acquisition and processing module with the predicted data of the traffic flow simulation module, and extracting key features from the fused data, including current traffic flow, vehicle queue length, average speed and predicted future traffic flow trend. These features will serve as input to the dynamic signal optimization algorithm.
[0092] Dynamic signal optimization is performed using a dynamic signal optimization algorithm based on reinforcement learning. The reinforcement learning algorithm works in the following ways:
[0093] State definition: Define the current traffic state as the state s of the algorithm t , including traffic flow, vehicle queue length, action selection: according to the current state s t , the algorithm selects a signal timing scheme as action a t , Reward calculation: After the action is implemented, the reward r is calculated based on the performance of the traffic system t, including reduced waiting time for vehicles, reduced congestion, and strategy update: according to the reward r t and state transition, update strategy π(a t |s t ), that is, the probability of choosing different actions in different states.
[0094] Formula (Q-learning update rule in reinforcement learning): Among them, α is the learning rate, γ is the discount factor, Q(s t ,a t ) is the value function of a state-action pair.
[0095] Based on the calculation results of the dynamic signal optimization algorithm, the optimal signal timing plan is generated, including the green light duration and phase sequence information of the traffic light. The generated optimal signal timing plan is transmitted to the traffic light control system. The control system adjusts the actual timing of the traffic light according to the received signal timing plan, monitors the system status in real time, collects new traffic flow and vehicle driving status data, and feeds the new data back to the dynamic signal optimization algorithm for the next round of optimization calculations.
[0096] Embodiment 4
[0097] A simulation digital twin visualization technology system, the system comprising:
[0098] The traffic flow simulation module builds a high-precision traffic flow simulation model based on historical traffic flow data, road network layout, and vehicle driving rules information to simulate actual traffic operation conditions, including vehicle driving, intersection signal control, etc., and predict future traffic flow trends.
[0099] Deep mining and analysis of historical traffic flow data is carried out to build a traffic flow simulation model with high precision and strong predictive capabilities. The model can simulate various behaviors of vehicles during driving, such as acceleration, deceleration, lane changing, and following, as well as conflicts and coordination at intersections, thereby achieving a comprehensive simulation of actual traffic operation conditions. Through close integration with the digital twin module and the real-time data acquisition and processing module, this module can receive real-time traffic data feedback, dynamically adjust the simulation model, and improve prediction accuracy and real-time performance.
[0100] The digital twin module uses digital twin technology to build a virtual traffic scene corresponding to the actual traffic scene, reflecting the actual traffic operation conditions in real time, including vehicle position, speed, and traffic signal status information, providing real-time data support for traffic signal optimization.
[0101] By using advanced technology and combining high-precision map data, a three-dimensional virtual environment that is highly consistent with the actual traffic scene is constructed. This environment not only includes static elements such as roads and buildings, but can also dynamically display dynamic elements such as vehicles, pedestrians, and traffic signals. Through the Internet of Things technology, real-time traffic data collected by sensors, cameras and other equipment (such as vehicle location, speed, driving trajectory, traffic light status, etc.) is mapped to the virtual environment in real time, achieving seamless integration of virtual and reality, providing a user-friendly interactive interface, and allowing users to simulate different traffic management plans through interactive operations in the virtual environment (such as dragging vehicles, adjusting traffic light timing, etc.), and observe their effects in real time.
[0102] The real-time data collection and processing module collects traffic flow and vehicle driving status data in real time through sensors and camera equipment, and transmits it to the system for processing and analysis, extracting useful information for traffic signal optimization.
[0103] It supports the collection of traffic data from multiple data sources (such as traffic monitoring cameras, GPS tracking devices, vehicle sensors, social media, etc.) to ensure the comprehensiveness and accuracy of the data. It uses distributed computing and big data processing technology to quickly process and analyze massive traffic data and extract valuable information for traffic signal optimization (such as traffic flow, vehicle density, driving speed, congestion index, etc.).
[0104] The visualization display module uses visualization technology to graphically display the traffic flow data and signal timing plans in the simulation model and digital twin scene to the user, so that the user can intuitively understand the traffic operation status through the interface.
[0105] The visual display module also includes an interactive interface, allowing the user to adjust the signal timing plan as needed and view the adjusted traffic operation effect in real time.
[0106] It provides a variety of visual charts and maps (such as heat maps, streamline maps, animated simulations, etc.) to display changes in traffic flow data and signal timing plans from multiple dimensions. It also designs an intuitive and easy-to-use user interface, allowing users to flexibly view and compare traffic conditions at different times and in different areas through operations such as dragging, zooming, and filtering.
[0107] The dynamic signal optimization algorithm module automatically calculates the optimal signal timing plan based on the real-time collected traffic flow data and the prediction results of the simulation model through the dynamic signal optimization algorithm, and adjusts the actual timing of traffic lights in real time to reduce vehicle waiting time and traffic congestion.
[0108] Taking into account multiple optimization objectives such as traffic flow, vehicle waiting time, and traffic efficiency, the signal timing plan is dynamically adjusted to adapt to changes in traffic demand based on changes in real-time traffic data. For example, the green light time is automatically extended to alleviate congestion when traffic is congested, and the green light time is shortened to improve traffic efficiency when traffic flow decreases. When optimizing the signal timing plan, traffic safety factors are fully considered to avoid increased risks of traffic accidents due to improper signal timing.
[0109] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the same elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.
Claims
1. A method for visualization of simulation digital twin technology, characterized in that: The method includes: Establish a traffic flow simulation model to predict changes in traffic flow; Build a digital twin scenario corresponding to the actual traffic scenario to reflect the actual traffic operation situation in real time; Collect traffic flow and vehicle driving status data in real time; Process and analyze the collected data to extract useful information; Display traffic flow data and signal timing plans through visualization technology; Based on real-time data and the prediction results of the simulation model, the dynamic signal optimization algorithm automatically calculates the optimal signal timing plan and adjusts the actual timing of traffic lights.
2. According to claim 1, a method for visualization technology based on simulation digital twins is characterized in that: The method of establishing a traffic flow simulation model and predicting changes in traffic flow includes: Collect historical traffic flow data, basic information on road network layout and vehicle driving rules, and pre-process the collected data; Use graph theory to represent the road network, where nodes represent intersections and edges represent road segments, and define the physical and traffic properties of each road segment; The following model is used to describe the interaction between vehicles. The formula is: Among them, v n+1 (t+Δt) is the speed of the following vehicle at the future time, v n (t) is the speed of the preceding vehicle at the current moment, Δt is the time step, and T is the driver’s reaction time V(s n+1 (t)) is based on the vehicle spacing s n+1 (t) determine the expected speed; A lane-changing model is introduced to handle vehicle lane-changing behavior; Design signal phases and timing schemes, including the allocation of green, yellow and red light times, and consider the transition logic and conflict resolution mechanisms between different phases; According to the above model, the vehicle driving and intersection signal control process are simulated, and the simulation results, including traffic flow, vehicle delay and queue length indicators, are recorded and output.
3. According to claim 1, a method for visualization technology based on simulation digital twins is characterized in that: The method of constructing a digital twin scene corresponding to an actual traffic scene includes: Map physical objects in actual traffic scenarios to digital twin scenarios and establish a real-time data synchronization mechanism; Use 3D modeling technology to build virtual traffic scenes, and simulate road layout, vehicle driving trajectory and signal control status in a virtual environment based on the road network model and vehicle driving model; Connect real-time traffic data to the digital twin scene through interfaces and protocols, and use visualization technology to display real-time information on vehicle location, speed, and traffic signal status in a virtual environment; Add interactive elements, including buttons and sliders, to the digital twin scene, allowing users to adjust signal timing plans and view traffic operation conditions in different scenarios through the interface.
4. The method according to claim 1, characterized in that: The method for real-time collection of traffic flow and vehicle driving status data comprises: Deploy sensor equipment at key traffic nodes, including cameras, radars, and geomagnetic sensors at intersections and highway entrances and exits; Collect traffic flow, vehicle speed, vehicle type, and lane occupancy data from sensor devices in real time through wired and wireless methods; The collected data is fused to integrate the data from different sensors into a consistent information stream. The Kalman filter algorithm is used to estimate and predict the vehicle state. The Kalman filter state update equation is: in, is the updated state estimate, is the predicted state, K k is the Kalman gain, z k is the observed value, H k is the observation matrix; Store data in databases and data warehouses, and transmit collected data to traffic signal optimization systems.
5. The method of visualization technology based on simulation digital twin according to claim 1, characterized in that: The collected data is processed and analyzed to extract useful information, and the method comprises: Check if there are identical records in the dataset and remove duplicates; For missing and incomplete data fields, fill them in based on the context; For data containing noise, the Kalman filter algorithm is used to remove the noise; Use statistics to define the threshold of outliers and detect data points that exceed the threshold. Use the Z-score method to detect outliers: Where X is the data point, μ is the mean, σ is the standard deviation, and |Z|>3 is considered an outlier; Data aggregation and statistical analysis: Aggregate data by time intervals, calculate average flow and average speed indicators, aggregate data to different sections and intersections according to the road network layout, calculate traffic flow and congestion levels in each area, and use statistical methods to further analyze data to extract traffic flow patterns and congestion hotspot information; Key features for signal optimization are extracted from the processed data, including traffic flow peak, average waiting time, and intersection saturation.
6. The method according to claim 1, characterized in that: The method of displaying traffic flow data and signal timing scheme by visualization technology comprises: Obtain processed traffic flow data and signal timing plan data from the real-time data acquisition and processing module; Select visualization libraries and frameworks to create visualization charts and interfaces, determine the type and layout of visualization elements, use heat maps to display traffic congestion, and use kernel density estimation to generate heat maps, involving the following formulas: Among them, K is the kernel function, h is the bandwidth, and x i is the observed data point, n is the number of data points; Design a user-friendly interface, including navigation bars, toolbars, and chart areas, determine the data that needs to be visualized, and select appropriate visual representations for each data type; Map data onto visual elements; Graphically represent the signal timing scheme, including using different colors of lights to represent different signal light states and displaying the real-time status of the signal lights on a map; Use visualization tools and techniques to render the designed interface and data into visual charts; Optimize the visual interface, including adjusting colors, fonts, and layout.
7. The method according to claim 1, characterized in that: The method includes automatically calculating the optimal signal timing scheme based on the real-time data and the prediction results of the simulation model through a dynamic signal optimization algorithm, and adjusting the actual timing of the traffic lights. The real-time traffic flow and vehicle driving status data provided by the real-time data acquisition and processing module are integrated with the predicted data of the traffic flow simulation module; Extract key features from the fused data, including current traffic flow, vehicle queue length, average speed, and predicted future traffic flow trends; Use the dynamic signal optimization algorithm based on reinforcement learning to optimize dynamic signals; Generate the optimal signal timing plan based on the calculation results of the dynamic signal optimization algorithm; The generated optimal signal timing plan is transmitted to the traffic light control system, and the control system adjusts the actual timing of the traffic light according to the received signal timing plan.
8. The method of visualization technology based on simulation digital twin according to claim 7 is characterized in that: The dynamic signal optimization algorithm using reinforcement learning is used to perform dynamic signal optimization. The reinforcement learning algorithm works in the following manner: State definition: Define the current traffic state as the state s of the algorithm t , including traffic volume and vehicle queue length; Action selection: according to the current state s t , the algorithm selects a signal timing scheme as action a t ; Reward calculation: After the action is implemented, the reward r is calculated based on the performance of the traffic system t , including reduced vehicle waiting time and reduced congestion; Strategy update: According to the reward r t and state transition, update strategy π(a t |s t ), that is, the probability of choosing different actions in different states; formula: Among them, α is the learning rate, γ is the discount factor, Q(s t ,a t ) is the value function of a state-action pair.
9. A simulation digital twin visualization technology system, characterized in that: The system includes: Traffic flow simulation module, based on historical traffic flow data, road network layout, and vehicle driving rules information, builds a high-precision traffic flow simulation model to simulate actual traffic operation and predict future traffic flow trends; The digital twin module uses digital twin technology to build a virtual traffic scene corresponding to the actual traffic scene, reflecting the actual traffic operation situation in real time; Real-time data collection and processing module, which collects traffic flow and vehicle driving status data in real time through sensors and camera equipment, transmits it to the system for processing and analysis, and extracts useful information for traffic signal optimization; The visualization display module uses visualization technology to graphically display the traffic flow data and signal timing schemes in the simulation model and digital twin scene to the user, so that the user can intuitively understand the traffic operation status through the interface; The dynamic signal optimization algorithm module automatically calculates the optimal signal timing plan based on the real-time collected traffic flow data and the prediction results of the simulation model through the dynamic signal optimization algorithm, and adjusts the actual timing of traffic lights in real time to reduce vehicle waiting time and traffic congestion.
10. The simulation digital twin visualization technology system according to claim 9 is characterized in that: The visual display module also includes an interactive interface, allowing the user to adjust the signal timing plan as needed and view the adjusted traffic operation effect in real time.
Citation Information
Patent Citations
Traffic road condition analysis system based on digital twin technology
CN117649767A
Augmented reality system for visualization of traffic information in a transportation environment
US20190257666A1
Cited By
Method, device and system for controlling highway traffic flow
CN119207099A
Traffic flow prediction method and device, computer equipment and storage medium
CN119495194A
Traffic Flow Prediction Method, Device, Computer Equipment and Storage Medium
CN119495194B
Dynamic construction method for digital twinborn bodies of expressway
CN119694138A
Twin scene light dynamic adjustment method and device, computer equipment and storage medium
CN119767485A
